manugandham27

Multi Agent LLM Council

Name: Multi Agent LLM Council
Author: manugandham27

AI community

SOURCE https://github.com/manugandham27/Multi-Agent-LLM-Council

Description

Multi-LLM consensus & evaluation platform querying OpenAI, Gemini, Claude, DeepSeek & Mistral in parallel to calculate weighted consensus, measure vote entropy, and eliminate single-model hallucinations via independent judge verification.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

🏛️ Multi-Agent LLM Council

Ask multiple AI models. Compare their reasoning. Reach a transparent consensus.

[![Next.js](https://img.shields.io/badge/Frontend-Next.js%2014-000000?style=for-the-badge&logo=nextdotjs&logoColor=white)](https://nextjs.org/) [![Vercel](https://img.shields.io/badge/Vercel-Live_Production-000000?style=for-the-badge&logo=vercel&logoColor=white)](https://web-psi-six-97.vercel.app) [![NestJS](https://img.shields.io/badge/Backend-NestJS-E0234E?style=for-the-badge&logo=nestjs&logoColor=white)](https://nestjs.com/) [![FastAPI](https://img.shields.io/badge/AI_Service-FastAPI-009688?style=for-the-badge&logo=fastapi&logoColor=white)](https://fastapi.tiangolo.com/) [![Prisma](https://img.shields.io/badge/ORM-Prisma-2D3748?style=for-the-badge&logo=prisma&logoColor=white)](https://www.prisma.io/) [![License](https://img.shields.io/badge/License-MIT-blue?style=for-the-badge)](LICENSE)

[Live Demo](https://web-psi-six-97.vercel.app) • [Features](#-key-features) • [Architecture](#-system-architecture) • [Quickstart](#-quickstart-guide) • [Consensus Methodology](#-consensus-engine)

[!TIP] **🌐 Live Production Web Application**: Experience the deployed application live on Vercel at **[https://web-psi-six-97.vercel.app](https://web-psi-six-97.vercel.app)**!

[!IMPORTANT] **Multi-Agent LLM Council** is an enterprise-grade AI ensemble platform that queries multiple leading LLM providers (OpenAI GPT, Google Gemini, Anthropic Claude, DeepSeek, Mistral, and local Ollama models) in parallel, measures vote entropy/disagreement, executes weighted consensus algorithms, and invokes an independent Judge verifier to eliminate single-model hallucinations.

📖 About The Project

**Multi-Agent LLM Council** was built to solve the fundamental reliability problem in modern Artificial Intelligence: **single-model hallucinations and domain bias**.

By orchestrating an ensemble of competing LLM models in parallel, th